Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    numbers, quantities, time durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     genannten
    0.81
     však
    0.78
     BOOLE
    0.78
     aforesaid
    0.77
    ⎠
    0.76
    空格
    0.75
    泊
    0.74
    फिट
    0.74
     ovan
    0.74
     jedoch
    0.73
    POSITIVE LOGITS
    otry
    0.75
     systém
    0.71
    something
    0.66
    사이트
    0.66
     something
    0.63
     जाऊन
    0.62
     ইচ্ছে
    0.61
    नाच्या
    0.60
    eis
    0.59
    ̠
    0.59
    Act Density 0.033%

    No Known Activations